SOTAVerified

Super-Resolution

Super-Resolution is a task in computer vision that involves increasing the resolution of an image or video by generating missing high-frequency details from low-resolution input. The goal is to produce an output image with a higher resolution than the input image, while preserving the original content and structure.

( Credit: MemNet )

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 181–190 of 3874 papers

TitleStatusHype
Efficient Long-Range Attention Network for Image Super-resolutionCode2
Real-World Blind Super-Resolution via Feature Matching with Implicit High-Resolution PriorsCode2
Pix2NeRF: Unsupervised Conditional π-GAN for Single Image to Neural Radiance Fields TranslationCode2
Deep Constrained Least Squares for Blind Image Super-ResolutionCode2
Denoising Diffusion Restoration ModelsCode2
Pix2NeRF: Unsupervised Conditional p-GAN for Single Image to Neural Radiance Fields TranslationCode2
Investigating Tradeoffs in Real-World Video Super-ResolutionCode2
CogView: Mastering Text-to-Image Generation via TransformersCode2
Learning Continuous Image Representation with Local Implicit Image FunctionCode2
Fourier Neural Operator for Parametric Partial Differential EquationsCode2
Show:102550
← PrevPage 19 of 388Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1super-resolutionAverage PSNR20.41—Unverified